updated the upload functionality to handle large files and added a new image file
This commit is contained in:
@@ -9,12 +9,23 @@ The converted PDF is then processed by the main upload workflow for 4K image gen
|
||||
import os
|
||||
import subprocess
|
||||
import logging
|
||||
import signal
|
||||
import time
|
||||
|
||||
# Set up logging
|
||||
logging.basicConfig(level=logging.INFO)
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def cleanup_libreoffice_processes():
|
||||
"""Clean up any hanging LibreOffice processes"""
|
||||
try:
|
||||
subprocess.run(['pkill', '-f', 'soffice'], capture_output=True, timeout=10)
|
||||
time.sleep(1) # Give processes time to terminate
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to cleanup LibreOffice processes: {e}")
|
||||
|
||||
|
||||
def pptx_to_pdf_libreoffice(pptx_path, output_dir):
|
||||
"""
|
||||
Convert PPTX to PDF using LibreOffice for highest quality.
|
||||
@@ -30,6 +41,9 @@ def pptx_to_pdf_libreoffice(pptx_path, output_dir):
|
||||
str: Path to the generated PDF file, or None if conversion failed
|
||||
"""
|
||||
try:
|
||||
# Clean up any existing LibreOffice processes
|
||||
cleanup_libreoffice_processes()
|
||||
|
||||
# Ensure output directory exists
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
|
||||
@@ -39,14 +53,19 @@ def pptx_to_pdf_libreoffice(pptx_path, output_dir):
|
||||
'--headless',
|
||||
'--convert-to', 'pdf',
|
||||
'--outdir', output_dir,
|
||||
'--invisible', # Run without any UI
|
||||
'--nodefault', # Don't start with default template
|
||||
pptx_path
|
||||
]
|
||||
|
||||
logger.info(f"Converting PPTX to PDF using LibreOffice: {pptx_path}")
|
||||
result = subprocess.run(cmd, capture_output=True, text=True, timeout=120)
|
||||
# Increase timeout to 300 seconds (5 minutes) for large presentations
|
||||
result = subprocess.run(cmd, capture_output=True, text=True, timeout=300)
|
||||
|
||||
if result.returncode != 0:
|
||||
logger.error(f"LibreOffice conversion failed: {result.stderr}")
|
||||
logger.error(f"LibreOffice stdout: {result.stdout}")
|
||||
cleanup_libreoffice_processes() # Clean up on failure
|
||||
return None
|
||||
|
||||
# Find the generated PDF file
|
||||
@@ -55,16 +74,22 @@ def pptx_to_pdf_libreoffice(pptx_path, output_dir):
|
||||
|
||||
if os.path.exists(pdf_path):
|
||||
logger.info(f"PDF conversion successful: {pdf_path}")
|
||||
cleanup_libreoffice_processes() # Clean up after success
|
||||
return pdf_path
|
||||
else:
|
||||
logger.error(f"PDF file not found after conversion: {pdf_path}")
|
||||
cleanup_libreoffice_processes() # Clean up on failure
|
||||
return None
|
||||
|
||||
except subprocess.TimeoutExpired:
|
||||
logger.error("LibreOffice conversion timed out (120s)")
|
||||
logger.error("LibreOffice conversion timed out (300s)")
|
||||
cleanup_libreoffice_processes() # Clean up on timeout
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"Error in PPTX to PDF conversion: {e}")
|
||||
import traceback
|
||||
logger.error(f"Traceback: {traceback.format_exc()}")
|
||||
cleanup_libreoffice_processes() # Clean up on error
|
||||
return None
|
||||
|
||||
|
||||
|
||||
@@ -290,21 +290,33 @@ def process_pptx(input_file, output_folder, duration, target_type, target_id):
|
||||
|
||||
try:
|
||||
# Step 1: Convert PPTX to PDF using LibreOffice for vector quality
|
||||
print("Step 1: Converting PPTX to PDF...")
|
||||
from utils.pptx_converter import pptx_to_pdf_libreoffice
|
||||
pdf_file = pptx_to_pdf_libreoffice(input_file, output_folder)
|
||||
|
||||
if not pdf_file:
|
||||
print("Error: Failed to convert PPTX to PDF")
|
||||
print("This could be due to:")
|
||||
print("- LibreOffice not properly installed")
|
||||
print("- Corrupted PPTX file")
|
||||
print("- Insufficient memory")
|
||||
print("- File permission issues")
|
||||
return False
|
||||
|
||||
print(f"PPTX successfully converted to PDF: {pdf_file}")
|
||||
|
||||
# Step 2: Use the same PDF to images workflow as direct PDF uploads
|
||||
print("Step 2: Converting PDF to JPG images...")
|
||||
# Convert PDF to JPG images (300 DPI, same as PDF workflow)
|
||||
image_filenames = convert_pdf_to_images(pdf_file, output_folder, delete_pdf=True, dpi=300)
|
||||
|
||||
if not image_filenames:
|
||||
print("Error: Failed to convert PDF to images")
|
||||
print("This could be due to:")
|
||||
print("- poppler-utils not properly installed")
|
||||
print("- PDF corruption during conversion")
|
||||
print("- Insufficient disk space")
|
||||
print("- Memory issues during image processing")
|
||||
return False
|
||||
|
||||
print(f"Generated {len(image_filenames)} JPG images from PPTX → PDF")
|
||||
@@ -313,11 +325,14 @@ def process_pptx(input_file, output_folder, duration, target_type, target_id):
|
||||
if os.path.exists(input_file):
|
||||
os.remove(input_file)
|
||||
print(f"Original PPTX file deleted: {input_file}")
|
||||
|
||||
|
||||
# Step 4: Update playlist with generated images in sequential order
|
||||
print("Step 3: Adding images to playlist...")
|
||||
success = update_playlist_with_files(image_filenames, duration, target_type, target_id)
|
||||
if success:
|
||||
print(f"Successfully processed PPTX: {len(image_filenames)} images added to playlist")
|
||||
else:
|
||||
print("Error: Failed to add images to playlist database")
|
||||
return success
|
||||
|
||||
except Exception as e:
|
||||
|
||||
Reference in New Issue
Block a user